CN116167727B - Image analysis-based flow node identification and processing system - Google Patents

Image analysis-based flow node identification and processing system Download PDF

Info

Publication number
CN116167727B
CN116167727B CN202310450230.7A CN202310450230A CN116167727B CN 116167727 B CN116167727 B CN 116167727B CN 202310450230 A CN202310450230 A CN 202310450230A CN 116167727 B CN116167727 B CN 116167727B
Authority
CN
China
Prior art keywords
flow
flow chart
node
target task
flow node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310450230.7A
Other languages
Chinese (zh)
Other versions
CN116167727A (en
Inventor
于伟
倪培峰
张炜琛
靳雯
王全修
石江枫
赵洲洋
王林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Rich Information Technology Co ltd
Information And Communication Center Of Ministry Of Public Security
Original Assignee
Beijing Rich Information Technology Co ltd
Information And Communication Center Of Ministry Of Public Security
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Rich Information Technology Co ltd, Information And Communication Center Of Ministry Of Public Security filed Critical Beijing Rich Information Technology Co ltd
Priority to CN202310450230.7A priority Critical patent/CN116167727B/en
Publication of CN116167727A publication Critical patent/CN116167727A/en
Application granted granted Critical
Publication of CN116167727B publication Critical patent/CN116167727B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/14—Image acquisition
    • G06V30/148—Segmentation of character regions
    • G06V30/153—Segmentation of character regions using recognition of characters or words
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Character Input (AREA)

Abstract

The present application relates to the field of electrical digital data processing technology,in particular to a flow node identification and processing system based on image analysis. The system includes a processor and a memory having stored thereon computer readable instructions which when executed by the processor perform the steps of: s100, acquiring a target task flow chart; s200, acquiring a character string set A corresponding to a target task flow chart; s300, traversing A, for a n Entity identification is carried out, and a is obtained n Entity E in (B) n And corresponding attribute tags L n The method comprises the steps of carrying out a first treatment on the surface of the S400, obtaining an upper-lower hierarchical relationship F between flow nodes in a target task flow chart; s500, obtaining the types of all flow nodes in the target task flow chart; and S600, updating the preset table to obtain a first configuration table corresponding to the target task flow chart. The method and the device can automatically generate the configuration file based on the task flow chart, and improve the efficiency of generating the configuration file.

Description

Image analysis-based flow node identification and processing system
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a flow node identification and processing system based on image analysis.
Background
In the prior art, the approval process is generally realized based on a configuration file, the configuration file is generally manually constructed by a user according to a task flow chart, and when the task flow chart is modified, the corresponding configuration file is also required to be manually modified by the user. For a user, the readability of the configuration file is poor, the display is not visual enough, more human resources are needed for manually constructing and modifying the configuration file, and the efficiency is low; how to automatically generate a configuration file based on a task flow chart is a problem to be solved.
Disclosure of Invention
The invention aims to provide a process node identification and processing system based on image analysis, which is used for automatically generating configuration files based on task flow charts, reducing occupation of human resources and improving efficiency of generating the configuration files.
According to the invention, there is provided a process node identifying and processing system based on image analysis, comprising a processor and a memory, wherein the memory stores computer readable instructions, and the computer readable instructions realize the following steps when executed by the processor:
s100, a target task flow chart is obtained, wherein the target task flow chart comprises flow nodes and edges used for connecting the flow nodes.
S200, recognizing the target task flow chart by using an OCR model to obtain a character string set A= (a) corresponding to the target task flow chart 1 ,a 2 ,…,a n ,…,a N )，a n And (3) for the character string corresponding to the nth flow node of the target task flow chart, wherein the value range of N is 1 to N, and N is the number of the flow nodes included in the target task flow chart.
S300, traversing A, for a n Entity identification is carried out, and a is obtained n Entity E in (B) n And corresponding attribute tags L n ，E n =(e n,1 ,e n,2 ,…,e n,m ,…,e n,M )，e n,m Is a as n M is the M-th entity identified from the front to the back, the value range of M is 1 to M, and M is a n The number of intermediate entities; l (L) n =(l n,1 ,l n,2 ,…,l n,m ,…,l n,M )，l n,m E is n,m Corresponding attribute tags for characterizing the corresponding entity as an operatorRoles, operation contents, or operation types.
S400, obtaining an upper-lower hierarchical relationship F= (F) between the flow nodes in the target task flow chart according to the arrow direction of the edge for connecting the flow nodes 1 ,f 2 ,…,f n ,…,f N )，f n F, corresponding to the upper and lower hierarchical relationship of the nth flow node of the target task flow chart n =(f 1 n ,f 2 n )，f 1 n For the upper-level flow node corresponding to the nth flow node of the target task flow chart, f 2 n And the lower-level flow node corresponding to the nth flow node of the target task flow chart.
S500, obtaining the types of the flow nodes in the target task flow chart according to the upper-lower hierarchical relationship among the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart, wherein the types of the flow nodes comprise a start flow node type, an operation description flow node type, an operation result flow node type and an end flow node type.
S600, updating a preset table according to the upper and lower hierarchical relationship among the flow nodes in the target task flow chart, the types of the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart to obtain a first configuration table corresponding to the target task flow chart; the field names of the preset table comprise an operator role, operation content, operation type, current flow node, lower-level flow node and flow node type.
Compared with the prior art, the invention has at least the following beneficial effects:
the invention can acquire the character strings corresponding to the flow nodes in the target task flow chart by using the OCR model, and can acquire the entities in the character strings and the attribute labels corresponding to the entities by using the entity identification technology; by combining the arrow directions of the edges between the flow nodes, the invention can acquire the upper and lower hierarchical relationship between the flow nodes; therefore, the invention can further acquire the types of the flow nodes, and the preset table stores the field names of the roles of operators, the operation content, the operation types, the current flow nodes, the lower-level flow nodes and the flow node types, so that the invention can record the information related to the nodes in the corresponding positions of the preset table according to the upper-lower level relation among the flow nodes, the types corresponding to the flow nodes and the attribute labels, realize the update of the preset table and further acquire the first configuration table corresponding to the target task flow chart. The method and the device can automatically generate the corresponding configuration file based on the target task flow chart, reduce the occupation of human resources and improve the efficiency of generating the configuration file.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for identifying and processing a flow node based on image resolution according to an embodiment of the present invention;
fig. 2 is a flowchart of a target task according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
According to the invention, a flow node identification and processing system based on image analysis is provided, which comprises a processor and a memory, wherein the memory is stored with computer readable instructions, and the computer readable instructions realize the flow node identification and processing method based on the image analysis when being executed by the processor. As shown in fig. 1, the process node identification and processing method based on image analysis includes the following steps:
s100, a target task flow chart is obtained, wherein the target task flow chart comprises flow nodes and edges used for connecting the flow nodes.
As one example, a target task flow chart is shown in FIG. 2, which corresponds to an approval flow, and includes 11 flow nodes and 10 edges for connecting the flow nodes. Those skilled in the art will appreciate that a flowchart including any number of flow nodes and any number of edges falls within the scope of the present invention.
S200, recognizing the target task flow chart by using an OCR model to obtain a character string set A= (a) corresponding to the target task flow chart 1 ,a 2 ,…,a n ,…,a N )，a n And (3) for the character string corresponding to the nth flow node of the target task flow chart, wherein the value range of N is 1 to N, and N is the number of the flow nodes included in the target task flow chart.
As one embodiment, as shown in fig. 2, the target task flow chart is identified by using the OCR model to obtain a character string set a= (a) 1 ,a 2 ,…,a 11 )，a 1 In this embodiment, a is a character string corresponding to the 1 st flow node of the target task flow chart 1 To start with; a, a 2 In this embodiment, a is a character string corresponding to the 2 nd flow node of the target task flow chart 2 To submit the request; a, a 11 In this embodiment, a is a character string corresponding to the 11 th flow node of the target task flow chart 11 For approval.
Those skilled in the art will appreciate that OCR recognition models are prior art and will not be described in detail herein.
S300, traversing A, for a n Entity identification is carried out, and a is obtained n Entity E in (B) n And corresponding attribute tags L n ，E n =(e n,1 ,e n,2 ,…,e n,m ,…,e n,M )，e n,m Is a as n M is the M-th entity identified from the front to the back, the value range of M is 1 to M, and M is a n The number of intermediate entities; l (L) n =(l n,1 ,l n,2 ,…,l n,m ,…,l n,M )，l n,m E is n,m And the corresponding attribute label is used for representing that the corresponding entity is an operator role, an operation content or an operation type.
As one embodiment, as shown in FIG. 2, the target task flow chart uses OCR model to recognize the character string a corresponding to the 3 rd flow node obtained by the target task flow chart 3 For the manager to audit, pair a 3 The entity obtained by entity identification is respectively an administrator and an audit, wherein the attribute label corresponding to the administrator is used for representing the role of the administrator as an operator, and the attribute label corresponding to the audit is used for representing the audit as operation content; character string a corresponding to 4 th flow node obtained by using OCR model to identify target task flow chart 4 To not pass through, pair a 4 And the entity obtained by entity identification is not passed, and the not passed corresponding attribute label is used for representing that the not passed is an operation type. Alternatively, the operation types in the present invention include pass and fail.
According to the invention, a can be identified by using a named entity recognition model n And carrying out entity recognition, wherein the named entity recognition model can be provided with the entity corresponding to the operator role, the operation content and the operation type in the recognition text by a pre-training method. Those skilled in the art will appreciate that any named entity recognition model and method of training the named entity recognition model in the prior art fall within the scope of the present invention.
S400, obtaining an upper-lower hierarchical relationship F= (F) between the flow nodes in the target task flow chart according to the arrow direction of the edge for connecting the flow nodes 1 ,f 2 ,…,f n ,…,f N )，f n F, corresponding to the upper and lower hierarchical relationship of the nth flow node of the target task flow chart n =(f 1 n ,f 2 n )，f 1 n For the upper-level flow node corresponding to the nth flow node of the target task flow chart, f 2 n Corresponding to the nth flow node of the target task flow chartA lower level flow node.
As an embodiment, as shown in fig. 2, the arrow direction of the edge between the 1 st flow node and the 2 nd flow node points from the 1 st flow node to the 2 nd flow node, thereby determining that the 2 nd flow node is the lower level flow node of the 1 st flow node, and the 1 st flow node is the upper level flow node of the 2 nd flow node.
It should be understood that the number of upper-level flow nodes and the number of lower-level flow nodes corresponding to different flow nodes in the target task flow chart are different, and some flow nodes may not have upper-level flow nodes, but some flow nodes may have more than 1 upper-level flow nodes; some flow nodes may not have lower level flow nodes, while some flow nodes may have more than 1 lower level flow node.
Optionally, the arrow direction of the edges between the flow nodes in the target task flow chart is identified using a target detection method or OCR model. Those skilled in the art will appreciate that any method of capturing the direction of the arrow in the prior art falls within the scope of the present invention.
S500, obtaining the types of the flow nodes in the target task flow chart according to the upper-lower hierarchical relationship among the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart, wherein the types of the flow nodes comprise a start flow node type, an operation description flow node type, an operation result flow node type and an end flow node type.
Optionally, the obtaining the type of each flow node in the target task flow chart according to the upper-lower hierarchical relationship between the flow nodes in the target task flow chart and the attribute labels corresponding to each flow node in the target task flow chart includes:
s510, if f 1 n If the task is an empty set, judging the type of the nth flow node of the target task flow chart as a starting flow node type; otherwise, S520 is entered.
As one embodiment, the target task flow chart is shown in FIG. 2, and the type of the 1 st flow node is the type of the start flow node.
S520, if f 2 n If the task is the empty set, judging the type of the nth flow node of the target task flow chart as the type of the ending flow node; otherwise, S530 is entered.
As an embodiment, as shown in fig. 2, the type of the 11 th flow node is the end flow node type, and the types of the 5 th flow node (the corresponding character string recognized by the OCR model is not passed by the administrator's audit) and the 9 th flow node (the corresponding character string recognized by the OCR model is not passed by the approver's audit) are also the end flow node types.
S530, traversing L n If L n If the attribute label used for representing the operation type exists in the flow chart, judging the type of the nth flow node of the target task flow chart to be the operation result flow node type; otherwise, the type of the nth flow node of the target task flow chart is judged to be the operation description flow node type.
As an embodiment, as shown in fig. 2, attribute tags for characterizing operation types are present in attribute tags corresponding to the 4 th flow node (corresponding character string recognized by the OCR model is not passed and is an upper level flow node of the 5 th flow node), the 6 th flow node (corresponding character string recognized by the OCR model is passed and is a lower level flow node of the 3 rd flow node), the 8 th flow node (corresponding character string recognized by the OCR model is not passed and is an upper level flow node of the 9 th flow node), and the 10 th flow node (corresponding character string recognized by the OCR model is passed and is an upper level flow node of the 11 th flow node), and are not start flow nodes and end flow nodes, so the types of the 4 th, 6 th, 8 th and 10 th flow nodes are operation result flow node types.
And no attribute label used for representing the operation type exists in the attribute labels corresponding to the 2 nd flow node, the 3 rd flow node and the 7 th flow node (the corresponding character strings recognized by the OCR model are checked by the to-be-examined personnel) in the target task flow chart, so the types of the 2 nd flow node, the 3 rd flow node and the 7 th flow node are operation description flow node types.
Optionally, a trained neural network model with a function of distinguishing the flow node type can be used to judge the flow node type corresponding to each flow node. Optionally, a large number of character strings corresponding to the process nodes are used as a training sample set, and the neural network model is trained by adopting a supervised training method, so that the trained neural network model has the function of judging the type of the process nodes.
S600, updating a preset table according to the upper and lower hierarchical relationship among the flow nodes in the target task flow chart, the types of the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart to obtain a first configuration table corresponding to the target task flow chart; the field names of the preset table comprise an operator role, operation content, operation type, current flow node, lower-level flow node and flow node type.
Optionally, updating the preset table to obtain a first configuration table corresponding to the target task flow chart includes:
s610, if the nth flow node is the operation description flow node type, entering S620; if the nth flow node is the start flow node type, then S630 is entered; if the nth flow node is of the end flow node type, then S640 is entered.
S620, obtaining f 2 n The number P of the lower-level flow nodes of the operation result flow node type included in the list is used for generating a record R taking the nth flow node as the current flow node in a preset list n ，R n =(r n,1 ,r n,2 ,…,r n,p ,…,r n,P )，r n,p For the P-th record taking the n-th flow node as the current flow node, the value range of P is 1 to P; r is (r) n,p The position corresponding to the operator role field name in the preset table is used for recording a n The corresponding attribute label in the list is an entity of an operation type, r n,p The position corresponding to the field name of the operation content in the preset table is used for recording a n The corresponding attribute label in the list is the entity of the operation content, r n,p Corresponds to a preset table middle operationLocation of type field name for record b n,p The corresponding attribute label in (b) is an entity of the operation type n,p Is f 2 n Lower-level flow node c of the p-th operation result flow node type included in the list n,p Corresponding character string, r n,p The position corresponding to the field name of the lower-level flow node in the preset table is used for recording c n,p Lower level flow node, r n,p The position corresponding to the field name of the flow node type in the preset table is used for recording a preset character string for representing the current flow node as an intermediate flow node.
According to the invention, if f 2 n The lower-level flow nodes included in the operation description flow node type are in addition to the operation result flow node type, and the record that the lower-level flow node corresponding to the nth flow node is the operation description flow node type flow node is also generated in the preset table, and optionally, f is acquired 2 n The operation included in the list describes the number Y of lower-level flow nodes of the flow node type, and a record Z taking the nth flow node as the current flow node is generated in a preset table n ，Z n =(z n,1 ,z n,2 ,…,z n,y ,…,z n,Y )，z n,y For the Y record taking the nth flow node as the current flow node, the value range of Y is 1 to Y; z n,y The position corresponding to the operator role field name in the preset table is used for recording a n The corresponding attribute label in (a) is the entity of the operator role, z n,y The position corresponding to the field name of the operation content in the preset table is used for recording a n The corresponding attribute label in the list is the entity of the operation content, z n,y The position corresponding to the operation type field name in the preset table is used for recording the preset character string for representing the no operation type, and z n,y The position corresponding to the field name of the lower-level flow node in the preset table is used for recording f 2 n The y-th operation included in the list describes the lower-level flow node of the flow node type, z n,y The position corresponding to the field name of the flow node type in the preset table is used for recording the information used for representing the current flow node as the intermediate flow nodePresetting a character string.
S630, obtain f 2 n The operation included in the list describes the number D of the lower-level flow nodes of the flow node type, and a record H taking the nth flow node as the current flow node is generated in a preset table n ，H n =(h n,1 ,h n,2 ,…,h n,d ,…,h n,D )，h n,d For the D record taking the nth flow node as the current flow node, D has a value range of 1 to D; h is a n,d The position corresponding to the operator role field name in the preset table is used for recording the preset character string used for representing the no operator role, and h n,d The position corresponding to the field name of the operation content in the preset table is used for recording the preset character string for representing the non-operation content, and h n,d The position corresponding to the field name of the operation type in the preset table is used for recording the preset character string for representing the no operation type, and h n,d The position corresponding to the field name of the lower-level flow node in the preset table is used for recording f 2 n The d-th operation included in the list describes the lower-level flow node of the flow node type, h n,d The position corresponding to the field name of the flow node type in the preset table is used for recording a preset character string for representing the current flow node as the starting flow node.
S640, generating a record X taking the nth flow node as the current flow node in a preset table n ；X n The position corresponding to the operator role field name in the preset table is used for recording the preset character string used for representing the no operator role, X n The position corresponding to the field name of the operation content in the preset table is used for recording the preset character string used for representing the non-operation content, X n The position corresponding to the operation type field name in the preset table is used for recording the preset character string for representing the no operation type, X n The position corresponding to the field name of the lower-level flow node in the preset table is used for recording the preset character string used for representing the non-lower-level flow node, X n The position corresponding to the field name of the flow node type in the preset table is used for recording a preset character string for representing that the current flow node is an ending flow node.
The invention can acquire the character strings corresponding to the flow nodes in the target task flow chart by using the OCR model, and can acquire the entities in the character strings and the attribute labels corresponding to the entities by using the entity identification technology; by combining the arrow directions of the edges between the flow nodes, the invention can acquire the upper and lower hierarchical relationship between the flow nodes; therefore, the invention can further acquire the types of the flow nodes, and the preset table stores the field names of the roles of operators, the operation content, the operation types, the current flow nodes, the lower-level flow nodes and the flow node types, so that the invention can record the information related to the nodes in the corresponding positions of the preset table according to the upper-lower level relation among the flow nodes, the types corresponding to the flow nodes and the attribute labels, realize the update of the preset table and further acquire the first configuration table corresponding to the target task flow chart. The method and the device can automatically generate the corresponding configuration file based on the target task flow chart, reduce the occupation of human resources and improve the efficiency of generating the configuration file.
As a preferred embodiment, the method for identifying and processing the flow node based on image analysis further comprises the following steps:
and S700, generating a first task flow chart according to the first configuration table.
Optionally, generating the first task flow diagram according to the first configuration table includes:
s710, obtaining current flow nodes, operation types and lower-level flow nodes corresponding to all records in the first configuration table.
S720, generating a flow chart according to the current flow nodes, the operation types and the lower-level flow nodes corresponding to all records in the first configuration table, and recording the generated flow chart as a first task flow chart.
Alternatively, a markdown generation flow chart is used. The process of generating a flowchart using markdown is prior art and will not be described in detail here.
S800, comparing whether the first task flow chart is the same as the target task flow chart; if the first configuration table is the same, judging that the first configuration table is correct; otherwise, determining that the first configuration table has an error.
For the user, the flow chart has better readability, is more visual and is convenient to understand, and optionally, whether the first task flow chart is the same as the target task flow chart or not is compared in a manual mode. According to the invention, when the first configuration table is judged to have errors, the first configuration table is manually modified by a user until the modification is correct.
The process node identifying and processing method based on image analysis in this embodiment further includes a process of verifying whether the first configuration table is correct, so that adverse effects caused by errors in the first configuration table generated based on S100-S600 can be avoided.
As a preferred embodiment, the method for identifying and processing the flow node based on image analysis further comprises the following steps:
s001, if a second task flow chart of the corresponding configuration table to be generated is detected, generating the corresponding second configuration table according to the second task flow chart.
According to the invention, if the second task flow chart of the corresponding configuration table to be generated is detected, the second configuration table corresponding to the second task flow chart is generated according to the method for generating the first configuration table corresponding to the target task flow chart.
And S002, if the second configuration table is correct, matching the graph name of the second task flow chart with the graph name of the target task flow chart.
According to the invention, if the second configuration table is incorrect, the second configuration table is modified until the second configuration table is correct, and then the graph name of the second task flow chart is matched with the graph name of the target task flow chart.
According to the invention, the detected second task flow chart of the corresponding configuration table to be generated can be a new task corresponding flow chart or can be used for replacing the target task flow chart (namely, modifying the target task flow chart), therefore, the invention matches the graph name of the second task flow chart with the graph name of the target task flow chart, and if the matching is successful, the second task flow chart is judged to be used for replacing the target task flow chart; if the matching is unsuccessful, the second task flow chart is judged to be the flow chart corresponding to the trusted task, and the association with the target task flow chart is smaller.
It should be understood that the graph names of the flowcharts are in the form of character strings, and optionally, by a method of character string comparison, whether the graph names of the second task flowchart and the graph names of the target task flowchart are matched is judged: if the character strings corresponding to the two flowcharts are the same, judging that the two flowcharts are matched; otherwise, the two flowcharts are not matched.
S003, if the graph name of the second task flow chart is matched with the graph name of the target task flow chart, outputting information of the position of the second configuration table different from the position of the first configuration table.
Optionally, traversing each record in the second configuration table row by row, and if a record in the second configuration table does not exist in the first configuration table, outputting the position information of the record in the second configuration table; and traversing each record in the first configuration table row by row, and outputting the position information of the record in the first configuration table if no record in the first configuration table exists in the second configuration table.
The embodiment can automatically identify the second task flow chart input by the user as the flow chart for replacing the target task flow chart, and can output the information of the position of the second configuration table different from the first configuration table, so that the user can quickly acquire the improved position of the second task flow chart compared with the target task flow chart.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the invention is defined by the appended claims.

Claims (4)

1. A process node identification and processing system based on image parsing, comprising a processor and a memory, wherein the memory stores computer readable instructions, which when executed by the processor, implement the steps of:
s100, acquiring a target task flow chart, wherein the target task flow chart comprises flow nodes and edges used for connecting the flow nodes;
s200, recognizing the target task flow chart by using an OCR model to obtain a character string set A= (a) corresponding to the target task flow chart 1 ,a 2 ,…,a n ,…,a N )，a n The method comprises the steps that a character string corresponding to an nth flow node of the target task flow chart is provided, the value range of N is 1 to N, and N is the number of flow nodes included in the target task flow chart;
s300, traversing A, for a n Entity identification is carried out, and a is obtained n Entity E in (B) n And corresponding attribute tags L n ，E n =(e n,1 ,e n,2 ,…,e n,m ,…,e n,M )，e n,m Is a as n M is the M-th entity identified from the front to the back, the value range of M is 1 to M, and M is a n The number of intermediate entities; l (L) n =(l n,1 ,l n,2 ,…,l n,m ,…,l n,M )，l n,m E is n,m The corresponding attribute tags are used for representing that the corresponding entity is an operator role, an operation content or an operation type; the operation types include pass and fail;
s400, obtaining an upper-lower hierarchical relationship F= (F) between the flow nodes in the target task flow chart according to the arrow direction of the edge for connecting the flow nodes 1 ,f 2 ,…,f n ,…,f N )，f n F, corresponding to the upper and lower hierarchical relationship of the nth flow node of the target task flow chart n =(f 1 n ,f 2 n )，f 1 n For the upper-level flow node corresponding to the nth flow node of the target task flow chart, f 2 n A lower-level flow node corresponding to an nth flow node of the target task flow chart;
s500, obtaining the types of the flow nodes in the target task flow chart according to the upper and lower hierarchical relationship among the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart, wherein the types of the flow nodes comprise a start flow node type, an operation description flow node type, an operation result flow node type and an end flow node type;
s600, updating a preset table according to the upper and lower hierarchical relationship among the flow nodes in the target task flow chart, the types of the flow nodes in the target task flow chart and the attribute labels corresponding to the flow nodes in the target task flow chart to obtain a first configuration table corresponding to the target task flow chart; the field names of the preset table comprise an operator role, operation content, operation type, current flow node, lower-level flow node and flow node type;
the computer readable instructions when executed by the processor further implement the steps of:
s700, generating a first task flow chart according to the first configuration table;
s800, comparing whether the first task flow chart is the same as the target task flow chart; if the first configuration table is the same, judging that the first configuration table is correct; otherwise, judging that the first configuration table has errors;
the computer readable instructions when executed by the processor further implement the steps of:
s001, if a second task flow chart of a corresponding configuration table to be generated is detected, generating the corresponding second configuration table according to the second task flow chart;
s002, if the second configuration table is correct, matching the graph name of the second task flow chart with the graph name of the target task flow chart;
s003, if the graph name of the second task flow chart is matched with the graph name of the target task flow chart, outputting information of the position of the second configuration table different from the position of the first configuration table;
in S500, obtaining the type of each flow node in the target task flow chart according to the upper-lower hierarchical relationship between the flow nodes in the target task flow chart and the attribute labels corresponding to each flow node in the target task flow chart includes:
s510, if f 1 n If the task is an empty set, judging the type of the nth flow node of the target task flow chart as a starting flow node type; otherwise, go to S520;
s520, if f 2 n If the task is the empty set, judging the type of the nth flow node of the target task flow chart as the type of the ending flow node; otherwise, go to S530;
s530, traversing L n If L n If the attribute label used for representing the operation type exists in the flow chart, judging the type of the nth flow node of the target task flow chart to be the operation result flow node type; otherwise, judging the type of the nth flow node of the target task flow chart as the operation description flow node type;
in S600, updating the preset table according to the upper-lower hierarchical relationship between the flow nodes in the target task flow chart, the types of the flow nodes in the target task flow chart, and the attribute labels corresponding to the flow nodes in the target task flow chart, so as to obtain a first configuration table corresponding to the target task flow chart, which includes:
s610, if the nth flow node is the operation description flow node type, entering S620;
s620, obtaining f 2 n The number P of the lower-level flow nodes of the operation result flow node type included in the list is used for generating a record R taking the nth flow node as the current flow node in a preset list n ，R n =(r n,1 ,r n,2 ,…,r n,p ,…,r n,P )，r n,p For the P-th record taking the n-th flow node as the current flow node, the value range of P is 1 to P; r is (r) n,p The position corresponding to the operator role field name in the preset table is used for recording a n The corresponding attribute label in (a) is an entity of the operator role, r n,p The position corresponding to the field name of the operation content in the preset table is used for recording a n The corresponding attribute label in the list is the entity of the operation content, r n,p The position corresponding to the operation type field name in the preset table is used for recording b n,p The corresponding attribute label in (a) isEntity of the operation type, b n,p Is f 2 n Lower-level flow node c of the p-th operation result flow node type included in the list n,p Corresponding character string, r n,p The position corresponding to the field name of the lower-level flow node in the preset table is used for recording c n,p Lower level flow node, r n,p The position corresponding to the field name of the flow node type in the preset table is used for recording a preset character string for representing the current flow node as an intermediate flow node.
2. The image resolution-based flow node identification and processing system according to claim 1, wherein S610 further comprises: if the nth flow node is the start flow node type, then S630 is entered;
s630, obtain f 2 n The operation included in the list describes the number D of the lower-level flow nodes of the flow node type, and a record H taking the nth flow node as the current flow node is generated in a preset table n ，H n =(h n,1 ,h n,2 ,…,h n,d ,…,h n,D )，h n,d For the D record taking the nth flow node as the current flow node, D has a value range of 1 to D; h is a n,d The position corresponding to the operator role field name in the preset table is used for recording the preset character string used for representing the no operator role, and h n,d The position corresponding to the field name of the operation content in the preset table is used for recording the preset character string for representing the non-operation content, and h n,d The position corresponding to the field name of the operation type in the preset table is used for recording the preset character string for representing the no operation type, and h n,d The position corresponding to the field name of the lower-level flow node in the preset table is used for recording f 2 n The d-th operation included in the list describes the lower-level flow node of the flow node type, h n,d The position corresponding to the field name of the flow node type in the preset table is used for recording a preset character string for representing the current flow node as the starting flow node.
3. The image resolution based process node identification and processing system according to claim 1, wherein in S700, generating a first task flow graph according to the first configuration table comprises:
s710, acquiring current flow nodes, operation types and lower-level flow nodes corresponding to all records in the first configuration table;
s720, generating a flow chart according to the current flow nodes, the operation types and the lower-level flow nodes corresponding to all records in the first configuration table, and recording the generated flow chart as a first task flow chart.
4. The image resolution based flow node identification and processing system according to claim 3, wherein in S720, a flow chart is generated using markdown.
CN202310450230.7A 2023-04-25 2023-04-25 Image analysis-based flow node identification and processing system Active CN116167727B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310450230.7A CN116167727B (en) 2023-04-25 2023-04-25 Image analysis-based flow node identification and processing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310450230.7A CN116167727B (en) 2023-04-25 2023-04-25 Image analysis-based flow node identification and processing system

Publications (2)

Publication Number Publication Date
CN116167727A CN116167727A (en) 2023-05-26
CN116167727B true CN116167727B (en) 2023-07-14

Family

ID=86420461

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310450230.7A Active CN116167727B (en) 2023-04-25 2023-04-25 Image analysis-based flow node identification and processing system

Country Status (1)

Country Link
CN (1) CN116167727B (en)

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108563984B (en) * 2018-03-02 2021-12-03 山东科技大学 Automatic identification and understanding method of flow model diagram
CN109710240A (en) * 2018-11-09 2019-05-03 深圳壹账通智能科技有限公司 Flow chart decomposition method and system
US20220188721A1 (en) * 2019-01-07 2022-06-16 Mitchell Swan Method and system for valuing the movement and flow of data
CN112287742B (en) * 2020-06-22 2023-12-26 上海柯林布瑞信息技术有限公司 Method and device for analyzing flow chart in file, computing equipment and storage medium
CN115034200A (en) * 2021-03-04 2022-09-09 广东博智林机器人有限公司 Drawing information extraction method and device, electronic equipment and storage medium
CN115147096B (en) * 2022-09-06 2022-11-18 京华信息科技股份有限公司 OCR-based flow rapid modeling method and system

Also Published As

Publication number Publication date
CN116167727A (en) 2023-05-26

Similar Documents

Publication Publication Date Title
US6549752B2 (en) Apparatus and method accumulating cases to be learned
JP4829920B2 (en) Form automatic embedding method and apparatus, graphical user interface apparatus
CN111767228B (en) Interface testing method, device, equipment and medium based on artificial intelligence
CN111144191B (en) Font identification method, font identification device, electronic equipment and storage medium
US20140308650A1 (en) Evaluation control
US20200117577A1 (en) Scalable ai framework for test automation
US8768241B2 (en) System and method for representing digital assessments
CN111459967A (en) Structured query statement generation method and device, electronic equipment and medium
JP2003058034A (en) Marking processing method and marking processing system
CN112509661B (en) Methods, computing devices, and media for identifying physical examination reports
CN110705596A (en) White screen detection method and device, electronic equipment and storage medium
CN112381099A (en) Question recording system based on digital education resources
CN112699671B (en) Language labeling method, device, computer equipment and storage medium
US11620558B1 (en) Iterative machine learning based techniques for value-based defect analysis in large data sets
CN116167727B (en) Image analysis-based flow node identification and processing system
US11386263B2 (en) Automatic generation of form application
CN113705159A (en) Merchant name labeling method, device, equipment and storage medium
JP2004013813A (en) Information management system and method
US11663761B2 (en) Hand-drawn diagram recognition using visual arrow-relation detection
US20180018893A1 (en) Method and system for identifying marked response data on a manually filled paper form
CN111881294B (en) Corpus labeling system, corpus labeling method and storage medium
JP2002304401A (en) Device and method for processing questionnaire and program
CN114625872A (en) Risk auditing method, system and equipment based on global pointer and storage medium
CN114596604A (en) Identity verification method, device, equipment, storage medium and computer program product
CN112597990A (en) Judging and reading method and system of handwriting formula, terminal device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant